Federal Grant Evidence

xyz.utilityhouse由 utilityhouse.xyz 發布官方發布者v1.3.2更新於 Oct 27, 2026

Find U.S. federal grants and return cited hard-gate and award-history evidence packs.

發布方自己的服務：AgentReady Woo

已驗證Streamable HTTP可網頁執行知識與記憶商業與電商

概覽

AI 產生的概覽

遠端 MCP 伺服器，用來查找美國聯邦補助機會，並回傳附引用的硬性門檻與補助歷史證據。

可以做什麼
  • 依主題搜尋目前與預告中的聯邦補助機會，回傳官方編號與來源連結
  • 列出某個機會的官方文件清單、目前修訂版本與完整性狀態
  • 擷取資格、相對配合款、截止日期、頁數限制與評審標準，並標明文件、頁碼與原文
  • 比較連續的官方修訂版本，逐項列出變更前後的值
  • 依非個人機構資料產生免費、附引用的硬性門檻初判
  • 申請版本化證據包，並可選擇針對某一特定機會提交證明
適用情境
適合在篩選美國聯邦補助機會時使用，希望把要求、截止日期與修訂變化追溯到 Grants.gov 官方文件，而不是依賴模型記憶的概述。適用於早期可行性初篩，不適用於法律資格判定或撰寫申請書。
執行需求
需要一個遠端 Streamable HTTP 端點；未宣告任何套件、API 金鑰或環境變數。提供面向不同用戶端的通道專用端點，README 列出 Claude、Gemini CLI、GitHub Copilot 及其他 Agent Plugins 用戶端的安裝方式。需要能連線至該託管服務的網路。
安裝前請注意
可選的證明工具會寫入資料：需聲明資料為最新、確認有意申請某一特定機會，並同意將衍生結果保留 30 天。完整證據包與證明共用每日 100 筆新發布結果的上限。此服務與 Grants.gov 無隸屬關係，不判定法律資格，也不預測補助結果。使用分析以彙總形式儲存。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Federal Grant Evidence，將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/xyz.utilityhouse%2Ffederal-grant-evidence/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "federal-grant-evidence": {
      "type": "http",
      "url": "https://grants.utilityhouse.xyz/mcp/registry"
    }
  }
}

README

Federal Grant Evidence MCP

Federal Grant Evidence is an independent UtilityHouse product for source-backed pursuit screening of U.S. federal grant opportunities. It finds current Grants.gov records, compares a bounded non-personal organization profile with cited hard gates, and can return a versioned award-history evidence pack when the required official evidence is complete.

It does not determine legal eligibility, predict awards, draft applications, or submit applications. It is not affiliated with Grants.gov or the U.S. government.

[Federal Grant Evidence opportunity-screening interface]

Free-beta access

https://grants.utilityhouse.xyz/mcp

The full remote MCP surface advertises seven tools:

  • get_grant_document_manifest — list the official attachment set and its completeness state.
  • analyze_nofo_requirements — return source-located pre-award requirement evidence.
  • compare_grant_amendments — compare consecutive official revisions with before/after citations.
  • search_federal_grants — free discovery from current official records.
  • analyze_federal_grant — free cited hard-gate preview.
  • get_federal_grant_evidence_pack — complete versioned pack when available.
  • submit_federal_grant_profile_v2_beta — opt-in opportunity 359701 proof from user-attested current non-personal facts; raw profile not retained.

The hosted MCP endpoints below expose the full seven-tool surface. Apify is an intentional three-operation read-only subset for Actor users; it does not accept the opt-in proof write and its listing must say so explicitly.

All advertised tools are free during the limited beta. The complete pack and opt-in proof share a limit of 100 newly released results per UTC day. The proof path requires explicit current-fact attestation, explicit intent to apply to opportunity 359701, and explicit consent to retain only the derived result for 30 days. No wallet, payment authorization, or blockchain transaction is requested. A future paid release is separate and mainnet remains locked.

For aggregate channel attribution, directory and client integrations use equivalent channel-specific endpoints:

ChannelEndpoint
OpenAI / ChatGPThttps://grants.utilityhouse.xyz/mcp/openai
Claudehttps://grants.utilityhouse.xyz/mcp/claude
Official MCP Registryhttps://grants.utilityhouse.xyz/mcp/registry
Smitheryhttps://grants.utilityhouse.xyz/mcp/smithery
Cursorhttps://grants.utilityhouse.xyz/mcp/cursor
Glamahttps://grants.utilityhouse.xyz/mcp/glama
PulseMCPhttps://grants.utilityhouse.xyz/mcp/pulsemcp
Geminihttps://grants.utilityhouse.xyz/mcp/gemini
GitHub Copilothttps://grants.utilityhouse.xyz/mcp/copilot

Every endpoint exposes the same advertised tools and the same free-beta behavior. The service stores only aggregate Korea calendar date (Asia/Seoul), channel, tool, outcome, and count in usage analytics. The separate opt-in proof path stores a derived pointer-only pack and attestation receipt for 30 days after explicit consent, but never the raw profile. Usage analytics do not store caller identity, request bodies, organization profiles, result contents, wallet data, or transaction data.

Install

Agent Plugins clients

This repository implements Agent Plugins 1.0 with a root plugin.json and mcp.json. Compatible clients can install the repository directly.

Claude

Add a custom web connector with the Claude endpoint. In Claude Code:

sh
claude mcp add --transport http federal-grant-evidence https://grants.utilityhouse.xyz/mcp/claude

The repository also includes a validated Claude plugin manifest, remote MCP configuration, and a narrowly scoped tool-routing skill for submission to the official Claude Plugin Directory.

Gemini CLI

sh
gemini extensions install https://github.com/tytutueh13-sudo/federal-grant-evidence-mcp --auto-update

The repository is also tagged with gemini-cli-extension for Gemini's automatic extension-gallery discovery.

GitHub Copilot in VS Code

Install Federal Grant Evidence in VS Code

Or install from a terminal:

sh
code --add-mcp '{"name":"federal-grant-evidence","type":"http","url":"https://grants.utilityhouse.xyz/mcp/copilot"}'

GitHub Copilot cloud agent

Repository administrators can paste copilot-mcp.json into Settings → Copilot → MCP servers. It explicitly allowlists the advertised tools. Only the opt-in proof tool writes data, and it stores only the consented derived result and receipt.

Other Agent Plugin clients and Cursor

Install this Agent Plugin where supported, or add the matching Streamable HTTP endpoint above as a remote MCP server named federal-grant-evidence.

Documentation

來源：README.md，提交 252c82a

工具

7

get_grant_document_manifest

List a grant's official documents

Use this when the user needs to know which official documents a U.S. federal grant opportunity has, which revision is current, and whether the official record is complete. It returns every Full Announcement, revised announcement, supporting document and application package Grants.gov holds, with official download URLs. It does not read the documents, assess eligibility, predict an award, draft, or submit.

輸入參數opportunity_id必填

analyze_nofo_requirements

Read a grant's requirements from its official documents

Use this after the document manifest, when the user needs the requirements stated inside a U.S. federal grant's official announcement — eligibility, cost share, deadlines, page limits, required submissions and evaluation criteria — each with the document, page and exact source text it came from. It returns CONFIRMED, CONFLICT, UNKNOWN or EXTRACTION_INCOMPLETE per requirement and never fills a gap with an inference. It does not determine legal eligibility, predict an award, draft, or submit.

輸入參數claim_typesopportunity_id必填

compare_grant_amendments

Compare a grant's revisions

Use this when the user needs to know what changed between revisions of a U.S. federal grant opportunity — deadlines, cost share, eligibility, funding — with the before and after value for each change and how much it matters. It reads the official revision history and reports what Grants.gov itself declared changed alongside the computed difference. It does not read announcement documents, assess eligibility, predict an award, draft, or submit.

輸入參數opportunity_id必填since_revision

search_federal_grants

Search federal grants

Use this when the user needs to find current or forecasted U.S. federal grant opportunities by topic. It returns official identifiers and source URLs for follow-up analysis. Do not use it to decide eligibility, predict an award, write an application, or submit anything.

輸入參數limitquery必填

analyze_federal_grant

Analyze a federal grant

Use this when the user needs a sourced go/no-go pursuit screen for one U.S. federal grant using a non-personal organization profile and the official opportunity record. The current preview is always free and explicitly marks unresolved project relevance, document, or award-history evidence. Do not use it for discovery only, legal eligibility advice, award prediction, drafting, or submission.

輸入參數organization必填opportunity_id必填

get_federal_grant_evidence_pack

Get a complete federal grant evidence pack

Use this limited free-beta tool after search or preview when the user wants a complete, versioned hard-gate and award-history evidence pack for one U.S. federal grant. It never requests payment during the beta. The service has a global daily beta capacity and counts only newly released complete results; reuse request_id for retries. It does not evaluate semantic project relevance, determine legal eligibility, predict an award, draft, or submit.

輸入參數request_id必填organization必填opportunity_id必填

submit_federal_grant_profile_v2_beta

Test an actual non-personal profile during the free beta

Use this opt-in free-beta tool only when the user wants to test opportunity 359701 against current actual non-personal organization, project, and readiness facts. The user must explicitly attest that the facts are current, explicitly confirm intent to apply to this opportunity, and consent to storing the resulting pointer-only pack for 30 days. The raw profile, names, contact details, identifiers, narratives, documents, and credentials are not stored. Missing facts remain NEEDS_INPUT. It does not determine legal eligibility, predict an award, draft, or submit an application.

輸入參數profile必填request_id必填opportunity_id必填consent_to_store_pointer_only_result必填attest_current_actual_non_personal_facts必填attest_intends_to_apply_to_opportunity_359701必填

版本歷史

1
  1. v1.3.2最新Sep 16, 2026

評分

已滿足適用檢查項的 100%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

其他 Utilityhouse 整合

AgentReady Woo

xyz.utilityhouse官方發布者

一個遠端 MCP 伺服器，用來檢查公開 WooCommerce 商店對購物代理的可讀性，並執行店主授權的發布閘門。

Streamable HTTP可網頁執行
開發者工具5 個工具Oct 24, 2026

Woo Revenue Incident Graph

由 GitHub 帳號 tytutueh13-sudo 發布

一個遠端 MCP 伺服器，協助助理檢查 WooCommerce 商店的結帳與付款健康狀況、診斷營收故障，並在修復後驗證是否恢復。

Streamable HTTP可網頁執行
資料與分析4 個工具Oct 25, 2026

Federal Grant Evidence

由 GitHub 帳號 tytutueh13-sudo 發布

一個遠端 MCP 伺服器，協助助理尋找美國聯邦補助計畫，並回傳附引用的硬性資格條件與補助歷史證據包。

Streamable HTTP可網頁執行
商業與電商尚未收錄Oct 24, 2026